| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-captioning-on-flickr30k-captions-test | VL-T5 | #5 | CIDEr: 2.6SPICE: 2.0 |
| image-captioning-on-nocaps-val | VL-T5 | #3 | CIDEr: 4.4SPICE: 5.3 |
| visual-question-answering-on-vcr-q-a-test | VL-T5 | #5 | Accuracy: 75.3 |
| visual-question-answering-on-vcr-q-ar-test | VL-T5 | #4 | Accuracy: 58.9 |
| visual-question-answering-on-vcr-qa-r-test | VL-T5 | #5 | Accuracy: 77.8 |